linux/kernel/softirq.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
 *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
 */

#define pr_fmt(fmt) …

#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/local_lock.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/rcupdate.h>
#include <linux/ftrace.h>
#include <linux/smp.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/irq.h>
#include <linux/wait_bit.h>
#include <linux/workqueue.h>

#include <asm/softirq_stack.h>

#define CREATE_TRACE_POINTS
#include <trace/events/irq.h>

/*
   - No shared variables, all the data are CPU local.
   - If a softirq needs serialization, let it serialize itself
     by its own spinlocks.
   - Even if softirq is serialized, only local cpu is marked for
     execution. Hence, we get something sort of weak cpu binding.
     Though it is still not clear, will it result in better locality
     or will not.

   Examples:
   - NET RX softirq. It is multithreaded and does not require
     any global serialization.
   - NET TX softirq. It kicks software netdevice queues, hence
     it is logically serialized per device, but this serialization
     is invisible to common code.
   - Tasklets: serialized wrt itself.
 */

#ifndef __ARCH_IRQ_STAT
DEFINE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
#endif

static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;

DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

const char * const softirq_to_name[NR_SOFTIRQS] = …;

/*
 * we cannot loop indefinitely here to avoid userspace starvation,
 * but we also don't want to introduce a worst case 1/HZ latency
 * to the pending events, so lets the scheduler to balance
 * the softirq load for us.
 */
static void wakeup_softirqd(void)
{ … }

#ifdef CONFIG_TRACE_IRQFLAGS
DEFINE_PER_CPU(int, hardirqs_enabled);
DEFINE_PER_CPU(int, hardirq_context);
EXPORT_PER_CPU_SYMBOL_GPL(…);
EXPORT_PER_CPU_SYMBOL_GPL(…);
#endif

/*
 * SOFTIRQ_OFFSET usage:
 *
 * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
 * to a per CPU counter and to task::softirqs_disabled_cnt.
 *
 * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
 *   processing.
 *
 * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
 *   on local_bh_disable or local_bh_enable.
 *
 * This lets us distinguish between whether we are currently processing
 * softirq and whether we just have bh disabled.
 */
#ifdef CONFIG_PREEMPT_RT

/*
 * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
 * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
 * softirq disabled section to be preempted.
 *
 * The per task counter is used for softirq_count(), in_softirq() and
 * in_serving_softirqs() because these counts are only valid when the task
 * holding softirq_ctrl::lock is running.
 *
 * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
 * the task which is in a softirq disabled section is preempted or blocks.
 */
struct softirq_ctrl {
	local_lock_t	lock;
	int		cnt;
};

static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
};

/**
 * local_bh_blocked() - Check for idle whether BH processing is blocked
 *
 * Returns false if the per CPU softirq::cnt is 0 otherwise true.
 *
 * This is invoked from the idle task to guard against false positive
 * softirq pending warnings, which would happen when the task which holds
 * softirq_ctrl::lock was the only running task on the CPU and blocks on
 * some other lock.
 */
bool local_bh_blocked(void)
{
	return __this_cpu_read(softirq_ctrl.cnt) != 0;
}

void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
	unsigned long flags;
	int newcnt;

	WARN_ON_ONCE(in_hardirq());

	/* First entry of a task into a BH disabled section? */
	if (!current->softirq_disable_cnt) {
		if (preemptible()) {
			local_lock(&softirq_ctrl.lock);
			/* Required to meet the RCU bottomhalf requirements. */
			rcu_read_lock();
		} else {
			DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
		}
	}

	/*
	 * Track the per CPU softirq disabled state. On RT this is per CPU
	 * state to allow preemption of bottom half disabled sections.
	 */
	newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
	/*
	 * Reflect the result in the task state to prevent recursion on the
	 * local lock and to make softirq_count() & al work.
	 */
	current->softirq_disable_cnt = newcnt;

	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
		raw_local_irq_save(flags);
		lockdep_softirqs_off(ip);
		raw_local_irq_restore(flags);
	}
}
EXPORT_SYMBOL(__local_bh_disable_ip);

static void __local_bh_enable(unsigned int cnt, bool unlock)
{
	unsigned long flags;
	int newcnt;

	DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
			    this_cpu_read(softirq_ctrl.cnt));

	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
		raw_local_irq_save(flags);
		lockdep_softirqs_on(_RET_IP_);
		raw_local_irq_restore(flags);
	}

	newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
	current->softirq_disable_cnt = newcnt;

	if (!newcnt && unlock) {
		rcu_read_unlock();
		local_unlock(&softirq_ctrl.lock);
	}
}

void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{
	bool preempt_on = preemptible();
	unsigned long flags;
	u32 pending;
	int curcnt;

	WARN_ON_ONCE(in_hardirq());
	lockdep_assert_irqs_enabled();

	local_irq_save(flags);
	curcnt = __this_cpu_read(softirq_ctrl.cnt);

	/*
	 * If this is not reenabling soft interrupts, no point in trying to
	 * run pending ones.
	 */
	if (curcnt != cnt)
		goto out;

	pending = local_softirq_pending();
	if (!pending)
		goto out;

	/*
	 * If this was called from non preemptible context, wake up the
	 * softirq daemon.
	 */
	if (!preempt_on) {
		wakeup_softirqd();
		goto out;
	}

	/*
	 * Adjust softirq count to SOFTIRQ_OFFSET which makes
	 * in_serving_softirq() become true.
	 */
	cnt = SOFTIRQ_OFFSET;
	__local_bh_enable(cnt, false);
	__do_softirq();

out:
	__local_bh_enable(cnt, preempt_on);
	local_irq_restore(flags);
}
EXPORT_SYMBOL(__local_bh_enable_ip);

/*
 * Invoked from ksoftirqd_run() outside of the interrupt disabled section
 * to acquire the per CPU local lock for reentrancy protection.
 */
static inline void ksoftirqd_run_begin(void)
{
	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
	local_irq_disable();
}

/* Counterpart to ksoftirqd_run_begin() */
static inline void ksoftirqd_run_end(void)
{
	__local_bh_enable(SOFTIRQ_OFFSET, true);
	WARN_ON_ONCE(in_interrupt());
	local_irq_enable();
}

static inline void softirq_handle_begin(void) { }
static inline void softirq_handle_end(void) { }

static inline bool should_wake_ksoftirqd(void)
{
	return !this_cpu_read(softirq_ctrl.cnt);
}

static inline void invoke_softirq(void)
{
	if (should_wake_ksoftirqd())
		wakeup_softirqd();
}

/*
 * flush_smp_call_function_queue() can raise a soft interrupt in a function
 * call. On RT kernels this is undesired and the only known functionality
 * in the block layer which does this is disabled on RT. If soft interrupts
 * get raised which haven't been raised before the flush, warn so it can be
 * investigated.
 */
void do_softirq_post_smp_call_flush(unsigned int was_pending)
{
	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
		invoke_softirq();
}

#else /* CONFIG_PREEMPT_RT */

/*
 * This one is for softirq.c-internal use, where hardirqs are disabled
 * legitimately:
 */
#ifdef CONFIG_TRACE_IRQFLAGS
void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{ … }
EXPORT_SYMBOL(…);
#endif /* CONFIG_TRACE_IRQFLAGS */

static void __local_bh_enable(unsigned int cnt)
{ … }

/*
 * Special-case - softirqs can safely be enabled by __do_softirq(),
 * without processing still-pending softirqs:
 */
void _local_bh_enable(void)
{ … }
EXPORT_SYMBOL(…);

void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
{ … }
EXPORT_SYMBOL(…);

static inline void softirq_handle_begin(void)
{ … }

static inline void softirq_handle_end(void)
{ … }

static inline void ksoftirqd_run_begin(void)
{ … }

static inline void ksoftirqd_run_end(void)
{ … }

static inline bool should_wake_ksoftirqd(void)
{ … }

static inline void invoke_softirq(void)
{ … }

asmlinkage __visible void do_softirq(void)
{ … }

#endif /* !CONFIG_PREEMPT_RT */

/*
 * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
 * but break the loop if need_resched() is set or after 2 ms.
 * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in
 * certain cases, such as stop_machine(), jiffies may cease to
 * increment and so we need the MAX_SOFTIRQ_RESTART limit as
 * well to make sure we eventually return from this method.
 *
 * These limits have been established via experimentation.
 * The two things to balance is latency against fairness -
 * we want to handle softirqs as soon as possible, but they
 * should not be able to lock up the box.
 */
#define MAX_SOFTIRQ_TIME …
#define MAX_SOFTIRQ_RESTART …

#ifdef CONFIG_TRACE_IRQFLAGS
/*
 * When we run softirqs from irq_exit() and thus on the hardirq stack we need
 * to keep the lockdep irq context tracking as tight as possible in order to
 * not miss-qualify lock contexts and miss possible deadlocks.
 */

static inline bool lockdep_softirq_start(void)
{ … }

static inline void lockdep_softirq_end(bool in_hardirq)
{ … }
#else
static inline bool lockdep_softirq_start(void) { return false; }
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif

static void handle_softirqs(bool ksirqd)
{ … }

asmlinkage __visible void __softirq_entry __do_softirq(void)
{ … }

/**
 * irq_enter_rcu - Enter an interrupt context with RCU watching
 */
void irq_enter_rcu(void)
{ … }

/**
 * irq_enter - Enter an interrupt context including RCU update
 */
void irq_enter(void)
{ … }

static inline void tick_irq_exit(void)
{ … }

static inline void __irq_exit_rcu(void)
{ … }

/**
 * irq_exit_rcu() - Exit an interrupt context without updating RCU
 *
 * Also processes softirqs if needed and possible.
 */
void irq_exit_rcu(void)
{ … }

/**
 * irq_exit - Exit an interrupt context, update RCU and lockdep
 *
 * Also processes softirqs if needed and possible.
 */
void irq_exit(void)
{ … }

/*
 * This function must run with irqs disabled!
 */
inline void raise_softirq_irqoff(unsigned int nr)
{ … }

void raise_softirq(unsigned int nr)
{ … }

void __raise_softirq_irqoff(unsigned int nr)
{ … }

void open_softirq(int nr, void (*action)(struct softirq_action *))
{ … }

/*
 * Tasklets
 */
struct tasklet_head { … };

static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);

static void __tasklet_schedule_common(struct tasklet_struct *t,
				      struct tasklet_head __percpu *headp,
				      unsigned int softirq_nr)
{ … }

void __tasklet_schedule(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL(…);

void __tasklet_hi_schedule(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL(…);

static bool tasklet_clear_sched(struct tasklet_struct *t)
{ … }

static void tasklet_action_common(struct softirq_action *a,
				  struct tasklet_head *tl_head,
				  unsigned int softirq_nr)
{ … }

static __latent_entropy void tasklet_action(struct softirq_action *a)
{ … }

static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
{ … }

void tasklet_setup(struct tasklet_struct *t,
		   void (*callback)(struct tasklet_struct *))
{ … }
EXPORT_SYMBOL(…);

void tasklet_init(struct tasklet_struct *t,
		  void (*func)(unsigned long), unsigned long data)
{ … }
EXPORT_SYMBOL(…);

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
/*
 * Do not use in new code. Waiting for tasklets from atomic contexts is
 * error prone and should be avoided.
 */
void tasklet_unlock_spin_wait(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL(…);
#endif

void tasklet_kill(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL(…);

#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
void tasklet_unlock(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL_GPL(…);

void tasklet_unlock_wait(struct tasklet_struct *t)
{ … }
EXPORT_SYMBOL_GPL(…);
#endif

void __init softirq_init(void)
{ … }

static int ksoftirqd_should_run(unsigned int cpu)
{ … }

static void run_ksoftirqd(unsigned int cpu)
{ … }

#ifdef CONFIG_HOTPLUG_CPU
static int takeover_tasklets(unsigned int cpu)
{ … }
#else
#define takeover_tasklets …
#endif /* CONFIG_HOTPLUG_CPU */

static struct smp_hotplug_thread softirq_threads = …;

static __init int spawn_ksoftirqd(void)
{ … }
early_initcall(spawn_ksoftirqd);

/*
 * [ These __weak aliases are kept in a separate compilation unit, so that
 *   GCC does not inline them incorrectly. ]
 */

int __init __weak early_irq_init(void)
{ … }

int __init __weak arch_probe_nr_irqs(void)
{ … }

int __init __weak arch_early_irq_init(void)
{ … }

unsigned int __weak arch_dynirq_lower_bound(unsigned int from)
{ … }